GraphMind: From Operational Traces to Self-Evolving Workflow Automation

• URL: http://arxiv.org/abs/2605.17617v2
• Date: Tue, 26 May 2026 00:01:30 GMT
• Title: GraphMind: From Operational Traces to Self-Evolving Workflow Automation
• Abstract summary: We present GraphMind, a system that constructs, executes, and evolves action-centric workflow graphs with minimal human effort.<n>The system has been deployed across four production cloud database services for incident investigation.<n>A 12-week field study confirms practical value: 97% of scored conversations yield actionable results within interactive latency.
• Score: 8.929269898719822
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Complex operational workflows coordinating personnel, tools, and information are central to system operations, yet end-to-end automation remains challenging due to extensive human input requirements and limited ability to adapt over time. We present GraphMind, a system that constructs, executes, and evolves action-centric workflow graphs with minimal human effort. The system operates in three phases. First, a scalable offline pipeline extracts structured workflow graphs from large volumes of human resolution traces, capturing problems, actions, and their causal relationships. Second, an online multi-agent traversal engine navigates the graph to dynamically construct and execute workflows, combining graph-guided retrieval with LLM-driven reasoning at each step. Third, Adaptive Traversal Reinforcement (ATR) reinforces successful traversal paths, enabling execution-informed graph adaptation. GraphMind has been deployed across four production cloud database services for incident investigation. Evaluated on 93 held-out incidents and validated via blind expert review, the system outperforms an Agentic Summary-RAG baseline in mitigation reach, hallucination rate, and diagnostic throughput while requiring 8x less retrieval context. The ATR layer reduces hallucination rate by 26%, demonstrating that workflow graphs can learn from execution feedback. A 12-week field study confirms practical value: 97% of scored conversations yield actionable results within interactive latency.

Related papers

• Inference-Time Graph Engineering for Multi-Agent LLM Workflows [51.56038180639833]
  We introduce ReActNet, a training-free framework that compiles a query and a set of role-specialized agents into a sequence of directed communication graphs.<n>We show that ReActNet consistently improves over fixed-topology and learned-topology baselines while maintaining competitive inference cost.
  arXiv  Detail & Related papers  (2026-09-04T23:32:11Z)
• GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks [43.75794490292518]
  Graph analysis requires agents to access data and execute operations in a graph environment.<n>Existing graph benchmarks for large language models (LLM) provide limited coverage of graph tasks and graph types.<n>We introduce GABench, a comprehensive benchmark for agentic graph analysis.
  arXiv  Detail & Related papers  (2026-08-03T04:18:31Z)
• Graph-Based Agentic AI with LangGraph: Workflow Pathways for Long-Running Stateful Business Processes [0.0]
  We present three executable recipes to show how typed state, conditional routing, deterministic tools, retries, interrupts, checkpoints, and traces fit together.<n>LangGraph is positioned by workflow-complexity fit, not as a universal default.
  arXiv  Detail & Related papers  (2026-07-21T17:07:13Z)
• GTA: Generating Long-Horizon Tasks for Web Agents at Scale [82.43869456830664]
  We introduce a scalable framework, GTA, that integrates crawling, retrieval-based seeding, in-context generation, and automated quality control.<n>We instantiate the pipeline on over 50 websites covering e-commerce, government, forums, and news, with multilingual and multi-hop coverage.<n>Our contributions are three-fold: (i) formalizing multi-hop web-agent task generation, (ii) proposing an efficient and validated pipeline for automatic data creation, and (iii) releasing a dynamic benchmark with reproducible evaluation.
  arXiv  Detail & Related papers  (2026-05-28T01:05:50Z)
• Learning Joint Embeddings of Function and Process Call Graphs for Malware Detection [10.970691047273254]
  Software systems can be represented as graphs, capturing dependencies among functions and processes.<n>This paper presents a pipeline for constructing and training Function Call Graphs (FCGs) and Process Call Graphs (PCGs) and learning joint embeddings.
  arXiv  Detail & Related papers  (2025-10-11T03:24:51Z)
• GraphTrafficGPT: Enhancing Traffic Management Through Graph-Based AI Agent Coordination [0.8999666725996978]
  GraphTrafficGPT represents tasks and dependencies as nodes and edges in a directed graph, enabling efficient parallel execution and dynamic resource allocation.<n>Brain Agent decomposes user queries, constructs optimized dependency graphs, and coordinates a network of specialized agents for data retrieval, analysis, visualization, and simulation.<n> Experimental results demonstrate that GraphTrafficGPT reduces token consumption by 50.2% and average response latency by 19.0% compared to TrafficGPT.
  arXiv  Detail & Related papers  (2025-07-17T19:41:09Z)
• GraphRunner: A Multi-Stage Framework for Efficient and Accurate Graph-Based Retrieval [3.792463570467098]
  GraphRunner is a novel graph-based retrieval framework that operates in three distinct stages: planning, verification, and execution.<n>It significantly reduces reasoning errors and detects hallucinations before execution.<n>Our evaluation using the GRBench dataset shows that GraphRunner consistently outperforms existing approaches.
  arXiv  Detail & Related papers  (2025-07-11T18:10:01Z)
• Follow the Flow: Fine-grained Flowchart Attribution with Neurosymbolic Agents [106.04963073116468]
  Flowcharts are a critical tool for visualizing decision-making processes.<n> vision-language models frequently hallucinate nonexistent connections and decision paths when analyzing these diagrams.<n>We introduce Fine-grained Flowchart, which traces specific components grounding a flowchart referring LLM response.<n>We propose FlowPathAgent, a neurosymbolic agent that performs fine-grained post hoc attribution through graph-based reasoning.
  arXiv  Detail & Related papers  (2025-06-02T06:02:41Z)
• GraphEdge: Dynamic Graph Partition and Task Scheduling for GNNs Computing in Edge Network [5.027047552301203]
  We propose GraphEdge, an efficient GNN-based edge computing architecture.<n>It considers the EC system of GNN tasks, where there are associations between users and it needs to take into account the task data of its neighbors.<n>Based on the optimized graph layout, our proposed deep reinforcement learning (DRL) based graph offloading algorithm (DRLGO) is executed.
  arXiv  Detail & Related papers  (2025-04-22T13:45:13Z)
• Plan-over-Graph: Towards Parallelable LLM Agent Schedule [53.834646147919436]
  Large Language Models (LLMs) have demonstrated exceptional abilities in reasoning for task planning.<n>This paper introduces a novel paradigm, plan-over-graph, in which the model first decomposes a real-life textual task into executable subtasks and constructs an abstract task graph.<n>The model then understands this task graph as input and generates a plan for parallel execution.
  arXiv  Detail & Related papers  (2025-02-20T13:47:51Z)
• AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials [53.376263056033046]
  Existing approaches rely on expensive human annotation, making them unsustainable at scale.<n>We propose AgentTrek, a scalable data synthesis pipeline that generates web agent trajectories by leveraging publicly available tutorials.<n>Our fully automated approach significantly reduces data collection costs, achieving a cost of just $0.55 per high-quality trajectory without human annotators.
  arXiv  Detail & Related papers  (2024-12-12T18:59:27Z)
• Research on the Application of Spark Streaming Real-Time Data Analysis System and large language model Intelligent Agents [1.4582633500696451]
  This study explores the integration of Agent AI with LangGraph to enhance real-time data analysis systems in big data environments.<n>The proposed framework overcomes limitations of static, inefficient stateful computations, and lack of human intervention.<n>System architecture incorporates Apache Spark Streaming, Kafka, and LangGraph to create a high-performance sentiment analysis system.
  arXiv  Detail & Related papers  (2024-12-10T05:51:11Z)
• LLM-Based Multi-Agent Systems are Scalable Graph Generative Models [73.28294528654885]
  GraphAgent-Generator (GAG) is a novel simulation-based framework for dynamic, text-attributed social graph generation.<n>GAG simulates the temporal node and edge generation processes for zero-shot social graph generation.<n>The resulting graphs exhibit adherence to seven key macroscopic network properties, achieving an 11% improvement in microscopic graph structure metrics.
  arXiv  Detail & Related papers  (2024-10-13T12:57:08Z)
• Can Graph Learning Improve Planning in LLM-based Agents? [61.47027387839096]
  Task planning in language agents is emerging as an important research topic alongside the development of large language models (LLMs) In this paper, we explore graph learning-based methods for task planning, a direction that is to the prevalent focus on prompt design. Our interest in graph learning stems from a theoretical discovery: the biases of attention and auto-regressive loss impede LLMs' ability to effectively navigate decision-making on graphs.
  arXiv  Detail & Related papers  (2024-05-29T14:26:24Z)
• A Versatile Graph Learning Approach through LLM-based Agent [33.37921145183175]
  We propose to explore versatile graph learning approaches with LLM-based agents. We develop several LLM-based agents equipped with diverse profiles, tools, functions and human experience. By evaluating on diverse tasks and graphs, the correct results of the agent and its comparable performance showcase the versatility of the proposed method.
  arXiv  Detail & Related papers  (2023-09-08T19:34:29Z)
• Co-attention Graph Pooling for Efficient Pairwise Graph Interaction Learning [19.58671020943416]
  Graph Neural Networks (GNNs) have proven to be effective in processing and learning from graph-structured data. We propose a novel and efficient graph-level approach for extracting interaction representations using co-attention in graph pooling. Our method, Co-Attention Graph Pooling (CAGPool), exhibits competitive performance relative to existing methods in both classification and regression tasks.
  arXiv  Detail & Related papers  (2023-07-28T07:53:34Z)
• EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learning [92.71579608528907]
  This paper aims to design an easy-to-use pipeline (termed as EasyDGL) composed of three key modules with both strong ability fitting and interpretability. EasyDGL can effectively quantify the predictive power of frequency content that a model learn from the evolving graph data.
  arXiv  Detail & Related papers  (2023-03-22T06:35:08Z)
• Dynamic Graph Representation Learning via Graph Transformer Networks [41.570839291138114]
  We propose a Transformer-based dynamic graph learning method named Dynamic Graph Transformer (DGT) DGT has spatial-temporal encoding to effectively learn graph topology and capture implicit links. We show that DGT presents superior performance compared with several state-of-the-art baselines.
  arXiv  Detail & Related papers  (2021-11-19T21:44:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.